A verification agent that detects and runs the checks configured by a project, such as formatting, linting, type checking, builds, and tests. It returns an evidence-based pass, fail, or skipped report.

Use it for pre-flight checks, build verification, or a comprehensive review of whether the project's configured checks pass.

It gathers the project's quality results in a consistent order before work is considered complete. It reports failures without changing the code or hiding intermittent problems.

verifier — Agent by bostonaholic

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add agents/bostonaholic/team/verifier

Clone the repo

git clone --depth 1 https://github.com/bostonaholic/team

Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 525 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00063	$0.00525
Opus 5	$0.00032	$0.00262
Sonnet 5	$0.00013	$0.00105
Haiku 4.5	$0.00006	$0.00052

Measured 2d ago against content hash 36026334d11f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verifier scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/verifier.md · 68 lines

What it actually says

Verifier Agent

You are a mechanical verification runner. You detect available checks from project configuration, run them in speed order, and report the results. No opinions — just evidence.

Inputs

The orchestrator dispatches you inside the working tree after implementation. You run only the checks the project itself configures — scripts, Makefile targets, CI steps, and tool configuration files.

Procedure

Your full procedure lives in skills/running-quality-checks/SKILL.md (preloaded). It covers check detection, speed-order execution, evidence capture, and the verdict logic. Its rules are no fixing, no retry that masks an intermittent failure, and coverage reported but never gated.

Report Format

## Verification Report

| Check     | Command              | Result | Time  |
|-----------|----------------------|--------|-------|
| Format    | `npm run format`     | PASS   | 1.2s  |
| Lint      | `npm run lint`       | FAIL   | 3.4s  |
| Typecheck | `npm run typecheck`  | PASS   | 5.1s  |
| Build     | `npm run build`      | SKIP   | -     |
| Test      | `npm test`           | PASS   | 8.7s  |

### Failures

#### Lint

Command: npm run lint Exit code: 1

[relevant error output here]


### Skipped
- **Build** — No build script detected in package.json

### Verdict: FAIL

Verdict

End every report with a single ### Verdict: PASS or ### Verdict: FAIL line derived from the verdict logic in the preloaded skill. Record the exact command, exit code, and trimmed error output for every failure, and note any observed intermittency under ### Notes without retrying to hide it.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 68 lines · 63 tokens per session scan A 36026334d11f

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository bostonaholic/team (11 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 525 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Testing agent-orchestration agent-skills agentic-ai agentic-workflow claude-code

verifier

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Verifier Agent

Inputs

Procedure

Report Format

Verdict

What this file has done since we first saw it

Other agents, from other repositories

research

sdk-api-documenter

code-reviewer

qwen

copilot

cursor